record_verdict

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the behavioral load. It does disclose a real trait – every quote is checked against the PDF and the verdict is rejected if a quote is not verbatim – which is more than the schema states. But it omits what 'rejected' looks like (error vs. silent drop), whether re-recording overwrites a prior verdict, and any permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, the core action front-loaded and the enforcement rule immediately after. Nothing is padding and nothing needs to be re-read.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter mutation tool with no annotations, no output schema, and 57% schema coverage, the description is adequate but thin. It never says what is returned on success, whether recording is idempotent, or how claim_id/key relate to the sibling lookup tools, leaving real gaps for an agent wiring this into a workflow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 57%, with the verdict enum, quotes, and issues well documented in the schema itself. The description's verbatim-quote rule adds meaning to the quotes parameter, but claim_id, key, and confidence remain undescribed in both places, so it only partially compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb+resource+scope: 'Record the verdict for one (claim, key) pair.' That is precise enough to distinguish it from read-oriented siblings like get_claim or list_claims, though it never names a sibling explicitly to sharpen the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: the quote-verification precondition tells the agent when the call will succeed, but there is no explicit 'use this after X' or comparison to alternatives such as verify_quote or audit_status. An agent can infer the workflow but must supply the context itself.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.